Every week we hold open seminars that cover recent achievements in the field of group's research and discuss our own projects.
Location: 4th floor, Times Center, Kantemirovskaya Str., 2A, St.Petersburg, Russia.
Day and time: Tuesday, 20:30-22:00.
Seminars are open to all. To receive announcements and other news, please contact Aleksei Shpilman (email@example.com).
2019Double Attention Networks
Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. On this seminar, we will discuss the “double attention block”, a novel (or not so novel) component from Facebook AI Research that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos. And also discuss their differences with SEnet’s.
And as a warmup we will have a little talk on how to read a paper since this is a kick-off for our yet another season of seminars.
Speaker: Rauf Kurbanov.
Presentation language: Russian.
Date and time: January 23rd, 18:30-20:00.
Location: Times, room 405.
Chen, Yunpeng, et al. “A^ 2-Nets: Double Attention Networks.” Advances in Neural Information Processing Systems. 2018.
Hu, Jie, Li Shen, and Gang Sun. “Squeeze-and-excitation networks.” arXiv preprint arXiv:1709.01507 7 (2017).
Keshav, S. "How to read a paper." ACM SIGCOMM Computer Communication Review 37.3 (2007): 83-84.
- About seminars
23 January 2019Double Attention Networks
27 November 2018Deep Multi-Agent Reinforcement Learning with Relevance Graphs
20 November 2018Adaptation of the domain for visual data.
13 November 2018The Conversational Intelligence Challenge
6 November 2018Learning to Run with Reward Shaping. Domain Adaptation for Gesture Recognition from sEMG.